Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
Open paper
Benchmark
Model
Rank
Results
monocular-depth-estimation-on-clevr-distance
SSF ViT-B/16 (VTAB-1k)
#8
Accuracy: 62.3
object-counting-on-clevr-count
SSF ViT-B/16 (VTAB-1k)
#9
Accuracy: 75.9
Rank counts only results with a code link.